DeepSeek V3.1 Terminus is slightly cheaper per million tokens (blended). DeepSeek V3.1 Terminus has the larger context window (163,840 vs 128,000 tokens).
DeepSeek V3 vs DeepSeek V3.1 Terminus
Live catalog fields. Best-in-row is highlighted.
DeepSeek V3open
DeepSeek · deepseek__deepseek-chat
DeepSeek V3.1 Terminusopen
DeepSeek · deepseek__deepseek-v3.1-terminus
Identity
| Field | deepseek__deepseek-chat | deepseek__deepseek-v3.1-terminus |
|---|---|---|
| Provider | DeepSeek | DeepSeek |
| Slug | deepseek__deepseek-chat | deepseek__deepseek-v3.1-terminus |
| Status | live | live |
| Open weights | Yes | Yes |
| License | — | — |
| HuggingFace | deepseek-ai/DeepSeek-V3 | deepseek-ai/DeepSeek-V3.1-Terminus |
Quality
| Field | deepseek__deepseek-chat | deepseek__deepseek-v3.1-terminus |
|---|---|---|
| Quality index (0–100) | — | — |
Cost
| Field | deepseek__deepseek-chat | deepseek__deepseek-v3.1-terminus |
|---|---|---|
| Input $ / 1M tokens | $0.26 | $0.27 |
| Cached input $ / 1M | — | — |
| Output $ / 1M tokens | $1.03 | $1.00 |
Context
| Field | deepseek__deepseek-chat | deepseek__deepseek-v3.1-terminus |
|---|---|---|
| Max context tokens | 128,000 | 163,840 |
| Max output tokens | 16,000 | 147,456 |
Modalities
| Field | deepseek__deepseek-chat | deepseek__deepseek-v3.1-terminus |
|---|---|---|
| Input | text | text |
| Output | text | text |